In [ ]:
!wget https://universe.roboflow.com/ds/Dj0NYYXhnu?key=tSVw3WtEQp
--2023-11-19 07:40:43-- https://universe.roboflow.com/ds/Dj0NYYXhnu?key=tSVw3WtEQp Resolving universe.roboflow.com (universe.roboflow.com)... 151.101.1.195, 151.101.65.195 Connecting to universe.roboflow.com (universe.roboflow.com)|151.101.1.195|:443... connected. HTTP request sent, awaiting response... 302 Found Location: https://storage.googleapis.com/roboflow-platform-exports/4OcoyBZTD8PYM96UKzLYsCHUzn82/WuAoqKB8YpgQ4eZLSgbK/13/yolov8.zip?X-Goog-Algorithm=GOOG4-RSA-SHA256&X-Goog-Credential=481589474394-compute%40developer.gserviceaccount.com%2F20231119%2Fauto%2Fstorage%2Fgoog4_request&X-Goog-Date=20231119T074043Z&X-Goog-Expires=901&X-Goog-SignedHeaders=host&X-Goog-Signature=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 [following] --2023-11-19 07:40:44-- https://storage.googleapis.com/roboflow-platform-exports/4OcoyBZTD8PYM96UKzLYsCHUzn82/WuAoqKB8YpgQ4eZLSgbK/13/yolov8.zip?X-Goog-Algorithm=GOOG4-RSA-SHA256&X-Goog-Credential=481589474394-compute%40developer.gserviceaccount.com%2F20231119%2Fauto%2Fstorage%2Fgoog4_request&X-Goog-Date=20231119T074043Z&X-Goog-Expires=901&X-Goog-SignedHeaders=host&X-Goog-Signature=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 Resolving storage.googleapis.com (storage.googleapis.com)... 142.250.136.207, 142.250.148.207, 64.233.191.207, ... Connecting to storage.googleapis.com (storage.googleapis.com)|142.250.136.207|:443... connected. HTTP request sent, awaiting response... 200 OK Length: 21373404 (20M) [application/zip] Saving to: ‘Dj0NYYXhnu?key=tSVw3WtEQp’ Dj0NYYXhnu?key=tSVw 100%[===================>] 20.38M --.-KB/s in 0.1s 2023-11-19 07:40:44 (158 MB/s) - ‘Dj0NYYXhnu?key=tSVw3WtEQp’ saved [21373404/21373404]
In [ ]:
In [ ]:
from google.colab import drive
drive.mount('/content/drive')
Mounted at /content/drive
In [ ]:
!unzip Dj0NYYXhnu?key=tSVw3WtEQp -d '/content/drive/MyDrive/Collision'
In [ ]:
!pip install clearml
Collecting clearml
Downloading clearml-1.13.2-py2.py3-none-any.whl (1.1 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 1.1/1.1 MB 7.7 MB/s eta 0:00:00
Requirement already satisfied: attrs>=18.0 in /usr/local/lib/python3.10/dist-packages (from clearml) (23.1.0)
Collecting furl>=2.0.0 (from clearml)
Downloading furl-2.1.3-py2.py3-none-any.whl (20 kB)
Requirement already satisfied: jsonschema>=2.6.0 in /usr/local/lib/python3.10/dist-packages (from clearml) (4.19.2)
Requirement already satisfied: numpy>=1.10 in /usr/local/lib/python3.10/dist-packages (from clearml) (1.23.5)
Collecting pathlib2>=2.3.0 (from clearml)
Downloading pathlib2-2.3.7.post1-py2.py3-none-any.whl (18 kB)
Requirement already satisfied: Pillow>=4.1.1 in /usr/local/lib/python3.10/dist-packages (from clearml) (9.4.0)
Requirement already satisfied: psutil>=3.4.2 in /usr/local/lib/python3.10/dist-packages (from clearml) (5.9.5)
Requirement already satisfied: pyparsing>=2.0.3 in /usr/local/lib/python3.10/dist-packages (from clearml) (3.1.1)
Requirement already satisfied: python-dateutil>=2.6.1 in /usr/local/lib/python3.10/dist-packages (from clearml) (2.8.2)
Requirement already satisfied: PyYAML>=3.12 in /usr/local/lib/python3.10/dist-packages (from clearml) (6.0.1)
Requirement already satisfied: requests>=2.20.0 in /usr/local/lib/python3.10/dist-packages (from clearml) (2.31.0)
Requirement already satisfied: six>=1.13.0 in /usr/local/lib/python3.10/dist-packages (from clearml) (1.16.0)
Requirement already satisfied: urllib3>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from clearml) (2.0.7)
Collecting pyjwt<2.9.0,>=2.4.0 (from clearml)
Downloading PyJWT-2.8.0-py3-none-any.whl (22 kB)
Requirement already satisfied: referencing<0.40 in /usr/local/lib/python3.10/dist-packages (from clearml) (0.31.0)
Collecting orderedmultidict>=1.0.1 (from furl>=2.0.0->clearml)
Downloading orderedmultidict-1.0.1-py2.py3-none-any.whl (11 kB)
Requirement already satisfied: jsonschema-specifications>=2023.03.6 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=2.6.0->clearml) (2023.11.1)
Requirement already satisfied: rpds-py>=0.7.1 in /usr/local/lib/python3.10/dist-packages (from jsonschema>=2.6.0->clearml) (0.12.0)
Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.20.0->clearml) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.20.0->clearml) (3.4)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.20.0->clearml) (2023.7.22)
Installing collected packages: pyjwt, pathlib2, orderedmultidict, furl, clearml
Attempting uninstall: pyjwt
Found existing installation: PyJWT 2.3.0
Uninstalling PyJWT-2.3.0:
Successfully uninstalled PyJWT-2.3.0
Successfully installed clearml-1.13.2 furl-2.1.3 orderedmultidict-1.0.1 pathlib2-2.3.7.post1 pyjwt-2.8.0
In [ ]:
!pip install ultralytics
Collecting ultralytics
Downloading ultralytics-8.0.212-py3-none-any.whl (645 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 645.2/645.2 kB 5.9 MB/s eta 0:00:00
Requirement already satisfied: matplotlib>=3.3.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (3.7.1)
Requirement already satisfied: numpy>=1.22.2 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (1.23.5)
Requirement already satisfied: opencv-python>=4.6.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (4.8.0.76)
Requirement already satisfied: pillow>=7.1.2 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (9.4.0)
Requirement already satisfied: pyyaml>=5.3.1 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (6.0.1)
Requirement already satisfied: requests>=2.23.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (2.31.0)
Requirement already satisfied: scipy>=1.4.1 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (1.11.3)
Requirement already satisfied: torch>=1.8.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (2.1.0+cu118)
Requirement already satisfied: torchvision>=0.9.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (0.16.0+cu118)
Requirement already satisfied: tqdm>=4.64.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (4.66.1)
Requirement already satisfied: pandas>=1.1.4 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (1.5.3)
Requirement already satisfied: seaborn>=0.11.0 in /usr/local/lib/python3.10/dist-packages (from ultralytics) (0.12.2)
Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from ultralytics) (5.9.5)
Requirement already satisfied: py-cpuinfo in /usr/local/lib/python3.10/dist-packages (from ultralytics) (9.0.0)
Collecting thop>=0.1.1 (from ultralytics)
Downloading thop-0.1.1.post2209072238-py3-none-any.whl (15 kB)
Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (1.2.0)
Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (0.12.1)
Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (4.44.3)
Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (1.4.5)
Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (23.2)
Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (3.1.1)
Requirement already satisfied: python-dateutil>=2.7 in /usr/local/lib/python3.10/dist-packages (from matplotlib>=3.3.0->ultralytics) (2.8.2)
Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=1.1.4->ultralytics) (2023.3.post1)
Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.23.0->ultralytics) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.23.0->ultralytics) (3.4)
Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.23.0->ultralytics) (2.0.7)
Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.23.0->ultralytics) (2023.7.22)
Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (3.13.1)
Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (4.5.0)
Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (1.12)
Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (3.2.1)
Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (3.1.2)
Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (2023.6.0)
Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.8.0->ultralytics) (2.1.0)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.7->matplotlib>=3.3.0->ultralytics) (1.16.0)
Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.8.0->ultralytics) (2.1.3)
Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.8.0->ultralytics) (1.3.0)
Installing collected packages: thop, ultralytics
Successfully installed thop-0.1.1.post2209072238 ultralytics-8.0.212
In [ ]:
!yolo
Arguments received: ['yolo']. Ultralytics 'yolo' commands use the following syntax:
yolo TASK MODE ARGS
Where TASK (optional) is one of ('detect', 'segment', 'classify', 'pose')
MODE (required) is one of ('train', 'val', 'predict', 'export', 'track', 'benchmark')
ARGS (optional) are any number of custom 'arg=value' pairs like 'imgsz=320' that override defaults.
See all ARGS at https://docs.ultralytics.com/usage/cfg or with 'yolo cfg'
1. Train a detection model for 10 epochs with an initial learning_rate of 0.01
yolo train data=coco128.yaml model=yolov8n.pt epochs=10 lr0=0.01
2. Predict a YouTube video using a pretrained segmentation model at image size 320:
yolo predict model=yolov8n-seg.pt source='https://youtu.be/LNwODJXcvt4' imgsz=320
3. Val a pretrained detection model at batch-size 1 and image size 640:
yolo val model=yolov8n.pt data=coco128.yaml batch=1 imgsz=640
4. Export a YOLOv8n classification model to ONNX format at image size 224 by 128 (no TASK required)
yolo export model=yolov8n-cls.pt format=onnx imgsz=224,128
5. Run special commands:
yolo help
yolo checks
yolo version
yolo settings
yolo copy-cfg
yolo cfg
Docs: https://docs.ultralytics.com
Community: https://community.ultralytics.com
GitHub: https://github.com/ultralytics/ultralytics
In [ ]:
!yolo task=detect mode=train model=yolov8l.pt imgsz=224 data="/content/drive/MyDrive/Collision/data.yaml" epochs=100 batch=124 name=/content/drive/MyDrive/Collision/final_training
Downloading https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8l.pt to 'yolov8l.pt'... 100% 83.7M/83.7M [00:00<00:00, 298MB/s] Ultralytics YOLOv8.0.212 🚀 Python-3.10.12 torch-2.1.0+cu118 CUDA:0 (Tesla T4, 15102MiB) engine/trainer: task=detect, mode=train, model=yolov8l.pt, data=/content/drive/MyDrive/Collision/data.yaml, epochs=100, patience=50, batch=124, imgsz=224, save=True, save_period=-1, cache=False, device=None, workers=8, project=None, name=final_training2, exist_ok=False, pretrained=True, optimizer=auto, verbose=True, seed=0, deterministic=True, single_cls=False, rect=False, cos_lr=False, close_mosaic=10, resume=False, amp=True, fraction=1.0, profile=False, freeze=None, overlap_mask=True, mask_ratio=4, dropout=0.0, val=True, split=val, save_json=False, save_hybrid=False, conf=None, iou=0.7, max_det=300, half=False, dnn=False, plots=True, source=None, show=False, save_txt=False, save_conf=False, save_crop=False, show_labels=True, show_conf=True, vid_stride=1, stream_buffer=False, line_width=None, visualize=False, augment=False, agnostic_nms=False, classes=None, retina_masks=False, boxes=True, format=torchscript, keras=False, optimize=False, int8=False, dynamic=False, simplify=False, opset=None, workspace=4, nms=False, lr0=0.01, lrf=0.01, momentum=0.937, weight_decay=0.0005, warmup_epochs=3.0, warmup_momentum=0.8, warmup_bias_lr=0.1, box=7.5, cls=0.5, dfl=1.5, pose=12.0, kobj=1.0, label_smoothing=0.0, nbs=64, hsv_h=0.015, hsv_s=0.7, hsv_v=0.4, degrees=0.0, translate=0.1, scale=0.5, shear=0.0, perspective=0.0, flipud=0.0, fliplr=0.5, mosaic=1.0, mixup=0.0, copy_paste=0.0, cfg=None, tracker=botsort.yaml, save_dir=/content/drive/MyDrive/Collision/final_training2 2023-11-19 07:53:07.197550: E tensorflow/compiler/xla/stream_executor/cuda/cuda_dnn.cc:9342] Unable to register cuDNN factory: Attempting to register factory for plugin cuDNN when one has already been registered 2023-11-19 07:53:07.197617: E tensorflow/compiler/xla/stream_executor/cuda/cuda_fft.cc:609] Unable to register cuFFT factory: Attempting to register factory for plugin cuFFT when one has already been registered 2023-11-19 07:53:07.197654: E tensorflow/compiler/xla/stream_executor/cuda/cuda_blas.cc:1518] Unable to register cuBLAS factory: Attempting to register factory for plugin cuBLAS when one has already been registered Overriding model.yaml nc=80 with nc=5 from n params module arguments 0 -1 1 1856 ultralytics.nn.modules.conv.Conv [3, 64, 3, 2] 1 -1 1 73984 ultralytics.nn.modules.conv.Conv [64, 128, 3, 2] 2 -1 3 279808 ultralytics.nn.modules.block.C2f [128, 128, 3, True] 3 -1 1 295424 ultralytics.nn.modules.conv.Conv [128, 256, 3, 2] 4 -1 6 2101248 ultralytics.nn.modules.block.C2f [256, 256, 6, True] 5 -1 1 1180672 ultralytics.nn.modules.conv.Conv [256, 512, 3, 2] 6 -1 6 8396800 ultralytics.nn.modules.block.C2f [512, 512, 6, True] 7 -1 1 2360320 ultralytics.nn.modules.conv.Conv [512, 512, 3, 2] 8 -1 3 4461568 ultralytics.nn.modules.block.C2f [512, 512, 3, True] 9 -1 1 656896 ultralytics.nn.modules.block.SPPF [512, 512, 5] 10 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 11 [-1, 6] 1 0 ultralytics.nn.modules.conv.Concat [1] 12 -1 3 4723712 ultralytics.nn.modules.block.C2f [1024, 512, 3] 13 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] 14 [-1, 4] 1 0 ultralytics.nn.modules.conv.Concat [1] 15 -1 3 1247744 ultralytics.nn.modules.block.C2f [768, 256, 3] 16 -1 1 590336 ultralytics.nn.modules.conv.Conv [256, 256, 3, 2] 17 [-1, 12] 1 0 ultralytics.nn.modules.conv.Concat [1] 18 -1 3 4592640 ultralytics.nn.modules.block.C2f [768, 512, 3] 19 -1 1 2360320 ultralytics.nn.modules.conv.Conv [512, 512, 3, 2] 20 [-1, 9] 1 0 ultralytics.nn.modules.conv.Concat [1] 21 -1 3 4723712 ultralytics.nn.modules.block.C2f [1024, 512, 3] 22 [15, 18, 21] 1 5586655 ultralytics.nn.modules.head.Detect [5, [256, 512, 512]] Model summary: 365 layers, 43633695 parameters, 43633679 gradients, 165.4 GFLOPs Transferred 589/595 items from pretrained weights WARNING ⚠️ ClearML installed but not initialized correctly, not logging this run. It seems ClearML is not configured on this machine! To get started with ClearML, setup your own 'clearml-server' or create a free account at https://app.clear.ml Setup instructions can be found here: https://clear.ml/docs TensorBoard: Start with 'tensorboard --logdir /content/drive/MyDrive/Collision/final_training2', view at http://localhost:6006/ Freezing layer 'model.22.dfl.conv.weight' AMP: running Automatic Mixed Precision (AMP) checks with YOLOv8n... AMP: checks passed ✅ train: Scanning /content/drive/MyDrive/Collision/train/labels.cache... 1431 images, 231 backgrounds, 0 corrupt: 100% 1431/1431 [00:00<?, ?it/s] albumentations: Blur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01), CLAHE(p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8)) val: Scanning /content/drive/MyDrive/Collision/valid/labels.cache... 350 images, 41 backgrounds, 0 corrupt: 100% 350/350 [00:00<?, ?it/s] Plotting labels to /content/drive/MyDrive/Collision/final_training2/labels.jpg... optimizer: 'optimizer=auto' found, ignoring 'lr0=0.01' and 'momentum=0.937' and determining best 'optimizer', 'lr0' and 'momentum' automatically... optimizer: AdamW(lr=0.001111, momentum=0.9) with parameter groups 97 weight(decay=0.0), 104 weight(decay=0.00096875), 103 bias(decay=0.0) Image sizes 224 train, 224 val Using 2 dataloader workers Logging results to /content/drive/MyDrive/Collision/final_training2 Starting training for 100 epochs... Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 1/100 9.88G 1.246 3.186 1.455 190 224: 100% 12/12 [00:12<00:00, 1.05s/it] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.68s/it] all 350 476 0.214 0.392 0.29 0.183 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 2/100 10.2G 1.058 1.501 1.336 176 224: 100% 12/12 [00:11<00:00, 1.01it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.46s/it] all 350 476 0.257 0.44 0.224 0.132 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 3/100 10.2G 1.08 1.417 1.371 183 224: 100% 12/12 [00:11<00:00, 1.05it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:05<00:00, 2.57s/it] all 350 476 0.154 0.599 0.148 0.0742 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 4/100 10.2G 1.168 1.458 1.402 172 224: 100% 12/12 [00:11<00:00, 1.07it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.13s/it] all 350 476 0.0219 0.264 0.0163 0.00478 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 5/100 10.2G 1.197 1.487 1.411 178 224: 100% 12/12 [00:11<00:00, 1.08it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.36s/it] all 350 476 0.000822 0.119 0.000624 0.000206 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 6/100 10.2G 1.228 1.517 1.442 175 224: 100% 12/12 [00:10<00:00, 1.14it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:05<00:00, 2.57s/it] all 350 476 0.0207 0.0655 0.00702 0.00205 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 7/100 10.2G 1.269 1.578 1.474 195 224: 100% 12/12 [00:11<00:00, 1.08it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.15s/it] all 350 476 0.313 0.223 0.0808 0.0302 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 8/100 10.2G 1.278 1.637 1.477 163 224: 100% 12/12 [00:12<00:00, 1.05s/it] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.76s/it] all 350 476 0.232 0.0385 0.0109 0.00489 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 9/100 10.2G 1.292 1.625 1.481 198 224: 100% 12/12 [00:10<00:00, 1.12it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:06<00:00, 3.17s/it] all 350 476 0.00231 0.0322 0.00112 0.000263 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 10/100 10.2G 1.295 1.654 1.476 203 224: 100% 12/12 [00:11<00:00, 1.01it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.49s/it] all 350 476 0.0681 0.153 0.0504 0.0202 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 11/100 10.2G 1.266 1.561 1.464 182 224: 100% 12/12 [00:12<00:00, 1.00s/it] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.49s/it] all 350 476 0.0499 0.216 0.0335 0.0131 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 12/100 10.2G 1.245 1.483 1.429 179 224: 100% 12/12 [00:11<00:00, 1.03it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.65s/it] all 350 476 0.0771 0.232 0.0928 0.058 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 13/100 10.2G 1.186 1.456 1.411 206 224: 100% 12/12 [00:10<00:00, 1.15it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.50s/it] all 350 476 0.529 0.172 0.0786 0.0353 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 14/100 10.2G 1.214 1.463 1.436 199 224: 100% 12/12 [00:11<00:00, 1.09it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.65s/it] all 350 476 0.508 0.182 0.113 0.0633 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 15/100 10.2G 1.176 1.447 1.408 195 224: 100% 12/12 [00:11<00:00, 1.05it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.68s/it] all 350 476 0.461 0.175 0.167 0.0729 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 16/100 10.2G 1.19 1.416 1.412 204 224: 100% 12/12 [00:12<00:00, 1.00s/it] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.48s/it] all 350 476 0.189 0.296 0.193 0.109 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 17/100 10.2G 1.123 1.36 1.379 193 224: 100% 12/12 [00:11<00:00, 1.06it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.89s/it] all 350 476 0.465 0.327 0.315 0.176 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 18/100 10.2G 1.106 1.309 1.366 166 224: 100% 12/12 [00:10<00:00, 1.16it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.44s/it] all 350 476 0.368 0.46 0.399 0.232 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 19/100 10.2G 1.084 1.266 1.353 193 224: 100% 12/12 [00:12<00:00, 1.02s/it] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.14s/it] all 350 476 0.495 0.413 0.426 0.265 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 20/100 10.2G 1.063 1.276 1.339 181 224: 100% 12/12 [00:11<00:00, 1.03it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.91s/it] all 350 476 0.316 0.422 0.333 0.192 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 21/100 10.2G 1.059 1.246 1.322 188 224: 100% 12/12 [00:09<00:00, 1.21it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:05<00:00, 2.57s/it] all 350 476 0.391 0.345 0.371 0.228 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 22/100 10.2G 1.064 1.241 1.333 163 224: 100% 12/12 [00:09<00:00, 1.22it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.48s/it] all 350 476 0.433 0.653 0.522 0.341 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 23/100 10.2G 1.056 1.188 1.338 164 224: 100% 12/12 [00:12<00:00, 1.01s/it] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.20s/it] all 350 476 0.411 0.558 0.485 0.317 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 24/100 10.2G 1.053 1.222 1.334 183 224: 100% 12/12 [00:11<00:00, 1.08it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.26s/it] all 350 476 0.326 0.51 0.404 0.257 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 25/100 10.2G 1.043 1.197 1.311 173 224: 100% 12/12 [00:11<00:00, 1.08it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.39s/it] all 350 476 0.407 0.565 0.466 0.296 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 26/100 10.2G 0.9993 1.155 1.298 180 224: 100% 12/12 [00:11<00:00, 1.06it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.02s/it] all 350 476 0.383 0.613 0.523 0.345 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 27/100 10.2G 1.015 1.109 1.298 165 224: 100% 12/12 [00:11<00:00, 1.01it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.99s/it] all 350 476 0.285 0.436 0.36 0.228 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 28/100 10.2G 0.9917 1.132 1.284 175 224: 100% 12/12 [00:11<00:00, 1.01it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.65s/it] all 350 476 0.264 0.399 0.312 0.2 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 29/100 10.2G 0.9918 1.115 1.286 191 224: 100% 12/12 [00:10<00:00, 1.12it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.36s/it] all 350 476 0.439 0.534 0.488 0.302 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 30/100 10.2G 0.9823 1.099 1.277 167 224: 100% 12/12 [00:11<00:00, 1.04it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.96s/it] all 350 476 0.248 0.369 0.306 0.19 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 31/100 10.2G 0.9661 1.051 1.26 190 224: 100% 12/12 [00:11<00:00, 1.09it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.35s/it] all 350 476 0.357 0.509 0.427 0.254 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 32/100 10.2G 0.9695 1.085 1.273 202 224: 100% 12/12 [00:10<00:00, 1.15it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:05<00:00, 2.69s/it] all 350 476 0.473 0.563 0.526 0.352 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 33/100 10.2G 0.955 1.058 1.26 197 224: 100% 12/12 [00:12<00:00, 1.02s/it] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.25s/it] all 350 476 0.494 0.586 0.535 0.335 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 34/100 10.2G 0.9541 1.039 1.264 178 224: 100% 12/12 [00:11<00:00, 1.03it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.67s/it] all 350 476 0.491 0.623 0.573 0.397 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 35/100 10.2G 0.9508 1.035 1.26 212 224: 100% 12/12 [00:10<00:00, 1.10it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.40s/it] all 350 476 0.537 0.566 0.543 0.359 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 36/100 10.2G 0.9296 1.013 1.248 209 224: 100% 12/12 [00:10<00:00, 1.16it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:05<00:00, 2.74s/it] all 350 476 0.477 0.551 0.459 0.314 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 37/100 10.2G 0.9188 1.011 1.246 181 224: 100% 12/12 [00:10<00:00, 1.10it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.38s/it] all 350 476 0.426 0.623 0.508 0.335 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 38/100 10.2G 0.9381 1.005 1.255 185 224: 100% 12/12 [00:11<00:00, 1.07it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.26s/it] all 350 476 0.449 0.549 0.476 0.321 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 39/100 10.2G 0.9124 0.9833 1.24 183 224: 100% 12/12 [00:11<00:00, 1.05it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.06s/it] all 350 476 0.48 0.554 0.519 0.357 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 40/100 10.2G 0.9099 0.979 1.223 203 224: 100% 12/12 [00:11<00:00, 1.06it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.05s/it] all 350 476 0.517 0.502 0.505 0.34 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 41/100 10.2G 0.901 0.957 1.225 185 224: 100% 12/12 [00:11<00:00, 1.03it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.89s/it] all 350 476 0.474 0.602 0.532 0.368 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 42/100 10.2G 0.9054 0.9466 1.218 187 224: 100% 12/12 [00:10<00:00, 1.09it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.34s/it] all 350 476 0.562 0.594 0.596 0.42 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 43/100 10.2G 0.8864 0.9145 1.21 177 224: 100% 12/12 [00:12<00:00, 1.05s/it] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.75s/it] all 350 476 0.569 0.66 0.56 0.37 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 44/100 10.2G 0.8758 0.9094 1.213 193 224: 100% 12/12 [00:12<00:00, 1.01s/it] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.38s/it] all 350 476 0.512 0.643 0.54 0.366 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 45/100 10.2G 0.8781 0.9357 1.207 193 224: 100% 12/12 [00:11<00:00, 1.04it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.72s/it] all 350 476 0.504 0.611 0.542 0.385 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 46/100 10.2G 0.8443 0.8987 1.191 192 224: 100% 12/12 [00:12<00:00, 1.03s/it] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.34s/it] all 350 476 0.512 0.652 0.581 0.421 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 47/100 10.2G 0.8651 0.8915 1.206 201 224: 100% 12/12 [00:11<00:00, 1.07it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.99s/it] all 350 476 0.562 0.618 0.599 0.431 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 48/100 10.2G 0.8571 0.9052 1.199 187 224: 100% 12/12 [00:12<00:00, 1.02s/it] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.01s/it] all 350 476 0.598 0.551 0.57 0.387 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 49/100 10.2G 0.8331 0.8975 1.196 176 224: 100% 12/12 [00:11<00:00, 1.05it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.85s/it] all 350 476 0.537 0.607 0.593 0.407 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 50/100 10.2G 0.8428 0.8591 1.181 192 224: 100% 12/12 [00:11<00:00, 1.03it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.67s/it] all 350 476 0.569 0.527 0.563 0.4 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 51/100 10.2G 0.8252 0.8499 1.177 192 224: 100% 12/12 [00:11<00:00, 1.02it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.68s/it] all 350 476 0.604 0.639 0.599 0.415 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 52/100 10.2G 0.8377 0.8499 1.189 161 224: 100% 12/12 [00:11<00:00, 1.00it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.50s/it] all 350 476 0.503 0.602 0.559 0.378 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 53/100 10.2G 0.8256 0.8579 1.181 191 224: 100% 12/12 [00:11<00:00, 1.07it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.06s/it] all 350 476 0.535 0.567 0.562 0.395 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 54/100 10.2G 0.8255 0.8277 1.178 189 224: 100% 12/12 [00:11<00:00, 1.08it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.01s/it] all 350 476 0.665 0.656 0.642 0.447 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 55/100 10.2G 0.8184 0.8304 1.171 203 224: 100% 12/12 [00:12<00:00, 1.02s/it] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.92s/it] all 350 476 0.492 0.589 0.555 0.375 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 56/100 10.2G 0.8017 0.8115 1.162 194 224: 100% 12/12 [00:12<00:00, 1.00s/it] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.46s/it] all 350 476 0.618 0.537 0.61 0.436 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 57/100 10.2G 0.7774 0.7734 1.149 181 224: 100% 12/12 [00:11<00:00, 1.07it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.79s/it] all 350 476 0.603 0.662 0.616 0.435 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 58/100 10.2G 0.7877 0.7767 1.153 185 224: 100% 12/12 [00:12<00:00, 1.00s/it] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.57s/it] all 350 476 0.555 0.659 0.602 0.434 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 59/100 10.2G 0.7905 0.7802 1.155 188 224: 100% 12/12 [00:11<00:00, 1.04it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.90s/it] all 350 476 0.715 0.571 0.639 0.465 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 60/100 10.2G 0.7939 0.7791 1.164 198 224: 100% 12/12 [00:11<00:00, 1.01it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.96s/it] all 350 476 0.503 0.572 0.533 0.364 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 61/100 10.2G 0.7769 0.7564 1.151 209 224: 100% 12/12 [00:11<00:00, 1.01it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.22s/it] all 350 476 0.594 0.678 0.64 0.453 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 62/100 10.2G 0.7641 0.7371 1.142 182 224: 100% 12/12 [00:11<00:00, 1.04it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.62s/it] all 350 476 0.659 0.51 0.6 0.421 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 63/100 10.2G 0.7428 0.7193 1.129 187 224: 100% 12/12 [00:11<00:00, 1.01it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.49s/it] all 350 476 0.59 0.587 0.593 0.423 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 64/100 10.2G 0.767 0.74 1.141 185 224: 100% 12/12 [00:11<00:00, 1.02it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.71s/it] all 350 476 0.589 0.606 0.609 0.437 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 65/100 10.2G 0.7477 0.7261 1.128 168 224: 100% 12/12 [00:11<00:00, 1.01it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.64s/it] all 350 476 0.593 0.581 0.607 0.438 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 66/100 10.2G 0.748 0.7369 1.131 189 224: 100% 12/12 [00:11<00:00, 1.04it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.77s/it] all 350 476 0.564 0.537 0.548 0.385 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 67/100 10.2G 0.7408 0.7193 1.122 170 224: 100% 12/12 [00:11<00:00, 1.04it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.74s/it] all 350 476 0.701 0.568 0.642 0.461 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 68/100 10.2G 0.743 0.718 1.132 188 224: 100% 12/12 [00:10<00:00, 1.11it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.63s/it] all 350 476 0.536 0.758 0.654 0.475 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 69/100 10.2G 0.7223 0.6736 1.125 190 224: 100% 12/12 [00:10<00:00, 1.16it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:05<00:00, 2.58s/it] all 350 476 0.582 0.683 0.621 0.456 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 70/100 10.2G 0.7198 0.6642 1.119 195 224: 100% 12/12 [00:11<00:00, 1.07it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.21s/it] all 350 476 0.636 0.664 0.676 0.501 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 71/100 10.2G 0.7002 0.6692 1.113 165 224: 100% 12/12 [00:11<00:00, 1.03it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.38s/it] all 350 476 0.675 0.602 0.636 0.468 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 72/100 10.2G 0.6945 0.6583 1.112 180 224: 100% 12/12 [00:10<00:00, 1.10it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.96s/it] all 350 476 0.605 0.636 0.617 0.448 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 73/100 10.2G 0.6988 0.6684 1.101 188 224: 100% 12/12 [00:11<00:00, 1.07it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.50s/it] all 350 476 0.677 0.615 0.634 0.456 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 74/100 10.2G 0.7206 0.6473 1.105 189 224: 100% 12/12 [00:10<00:00, 1.13it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.53s/it] all 350 476 0.583 0.683 0.607 0.431 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 75/100 10.2G 0.6988 0.6435 1.108 172 224: 100% 12/12 [00:11<00:00, 1.06it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.50s/it] all 350 476 0.599 0.666 0.632 0.462 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 76/100 10.2G 0.6854 0.6223 1.098 172 224: 100% 12/12 [00:11<00:00, 1.08it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.22s/it] all 350 476 0.613 0.674 0.642 0.482 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 77/100 10.2G 0.6663 0.6343 1.098 189 224: 100% 12/12 [00:11<00:00, 1.08it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.45s/it] all 350 476 0.666 0.62 0.649 0.483 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 78/100 10.2G 0.6688 0.6313 1.094 192 224: 100% 12/12 [00:11<00:00, 1.09it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.57s/it] all 350 476 0.628 0.653 0.659 0.495 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 79/100 10.2G 0.6736 0.62 1.088 214 224: 100% 12/12 [00:11<00:00, 1.02it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.37s/it] all 350 476 0.625 0.633 0.641 0.465 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 80/100 10.2G 0.6759 0.6201 1.088 181 224: 100% 12/12 [00:11<00:00, 1.07it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.77s/it] all 350 476 0.651 0.647 0.675 0.498 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 81/100 10.2G 0.6508 0.6011 1.085 202 224: 100% 12/12 [00:11<00:00, 1.01it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.40s/it] all 350 476 0.629 0.637 0.667 0.495 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 82/100 10.2G 0.655 0.5781 1.081 198 224: 100% 12/12 [00:11<00:00, 1.02it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.67s/it] all 350 476 0.65 0.607 0.631 0.461 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 83/100 10.2G 0.6463 0.5725 1.073 176 224: 100% 12/12 [00:11<00:00, 1.01it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.48s/it] all 350 476 0.555 0.661 0.612 0.444 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 84/100 10.2G 0.6572 0.5861 1.083 188 224: 100% 12/12 [00:11<00:00, 1.06it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.01s/it] all 350 476 0.561 0.645 0.629 0.452 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 85/100 10.2G 0.633 0.5594 1.076 187 224: 100% 12/12 [00:11<00:00, 1.07it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.02s/it] all 350 476 0.589 0.642 0.646 0.476 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 86/100 10.2G 0.6376 0.5726 1.075 194 224: 100% 12/12 [00:11<00:00, 1.02it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.87s/it] all 350 476 0.622 0.669 0.651 0.481 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 87/100 10.2G 0.6212 0.5627 1.068 177 224: 100% 12/12 [00:10<00:00, 1.11it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.20s/it] all 350 476 0.593 0.704 0.632 0.46 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 88/100 10.2G 0.6205 0.5586 1.067 190 224: 100% 12/12 [00:11<00:00, 1.06it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.87s/it] all 350 476 0.598 0.675 0.645 0.471 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 89/100 10.2G 0.6301 0.5457 1.07 202 224: 100% 12/12 [00:10<00:00, 1.11it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.29s/it] all 350 476 0.662 0.587 0.637 0.466 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 90/100 10.2G 0.6103 0.5363 1.067 168 224: 100% 12/12 [00:10<00:00, 1.10it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.08s/it] all 350 476 0.643 0.585 0.633 0.457 Closing dataloader mosaic albumentations: Blur(p=0.01, blur_limit=(3, 7)), MedianBlur(p=0.01, blur_limit=(3, 7)), ToGray(p=0.01), CLAHE(p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8)) Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 91/100 10.2G 0.4922 0.3841 0.9818 79 224: 100% 12/12 [00:15<00:00, 1.26s/it] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.14s/it] all 350 476 0.637 0.637 0.649 0.477 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 92/100 10.2G 0.4559 0.3331 0.9578 87 224: 100% 12/12 [00:11<00:00, 1.01it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.28s/it] all 350 476 0.641 0.651 0.642 0.464 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 93/100 10.2G 0.4606 0.3192 0.9559 84 224: 100% 12/12 [00:10<00:00, 1.13it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.90s/it] all 350 476 0.633 0.589 0.654 0.481 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 94/100 10.2G 0.4414 0.3044 0.9561 90 224: 100% 12/12 [00:10<00:00, 1.11it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.67s/it] all 350 476 0.611 0.627 0.652 0.48 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 95/100 10.2G 0.4323 0.2969 0.9515 89 224: 100% 12/12 [00:10<00:00, 1.12it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.57s/it] all 350 476 0.604 0.621 0.644 0.479 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 96/100 10.2G 0.4285 0.2915 0.9474 77 224: 100% 12/12 [00:10<00:00, 1.13it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.62s/it] all 350 476 0.595 0.649 0.654 0.481 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 97/100 10.2G 0.418 0.2792 0.9371 73 224: 100% 12/12 [00:11<00:00, 1.07it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.40s/it] all 350 476 0.665 0.608 0.653 0.485 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 98/100 10.2G 0.4229 0.2811 0.9401 72 224: 100% 12/12 [00:10<00:00, 1.11it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:03<00:00, 1.84s/it] all 350 476 0.662 0.565 0.651 0.487 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 99/100 10.2G 0.4052 0.2761 0.9294 71 224: 100% 12/12 [00:11<00:00, 1.09it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:02<00:00, 1.46s/it] all 350 476 0.722 0.54 0.657 0.49 Epoch GPU_mem box_loss cls_loss dfl_loss Instances Size 100/100 10.2G 0.3933 0.2687 0.9173 87 224: 100% 12/12 [00:10<00:00, 1.15it/s] Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:04<00:00, 2.07s/it] all 350 476 0.579 0.683 0.663 0.491 100 epochs completed in 0.530 hours. Optimizer stripped from /content/drive/MyDrive/Collision/final_training2/weights/last.pt, 87.6MB Optimizer stripped from /content/drive/MyDrive/Collision/final_training2/weights/best.pt, 87.6MB Validating /content/drive/MyDrive/Collision/final_training2/weights/best.pt... Ultralytics YOLOv8.0.212 🚀 Python-3.10.12 torch-2.1.0+cu118 CUDA:0 (Tesla T4, 15102MiB) Model summary (fused): 268 layers, 43610463 parameters, 0 gradients, 164.8 GFLOPs Class Images Instances Box(P R mAP50 mAP50-95): 100% 2/2 [00:05<00:00, 2.54s/it] all 350 476 0.636 0.664 0.675 0.501 fire 350 123 0.69 0.761 0.771 0.464 minor 350 17 0.541 0.624 0.564 0.517 moderate 350 36 0.586 0.472 0.517 0.408 no_accident 350 107 0.643 0.626 0.684 0.565 severe 350 193 0.718 0.834 0.841 0.552 Speed: 0.0ms preprocess, 2.7ms inference, 0.0ms loss, 2.7ms postprocess per image Results saved to /content/drive/MyDrive/Collision/final_training2 💡 Learn more at https://docs.ultralytics.com/modes/train
In [ ]:
In [ ]:
In [ ]:
In [ ]:
import gc
import tensorflow as tf
# Custom Callback To Include in Callbacks List At Training Time
class GarbageCollectorCallback(tf.keras.callbacks.Callback):
def on_epoch_end(self, epoch, logs=None):
gc.collect()
In [ ]:
In [ ]:
from ultralytics import YOLO
model = YOLO("/content/drive/MyDrive/Collision/final_training2/weights/best.pt")
model.export(format="onnx", imgsz=[224,224])
Ultralytics YOLOv8.0.212 🚀 Python-3.10.12 torch-2.1.0+cu118 CPU (Intel Xeon 2.30GHz) Model summary (fused): 268 layers, 43610463 parameters, 0 gradients, 164.8 GFLOPs PyTorch: starting from '/content/drive/MyDrive/Collision/final_training2/weights/best.pt' with input shape (1, 3, 224, 224) BCHW and output shape(s) (1, 9, 1029) (83.6 MB) ONNX: starting export with onnx 1.15.0 opset 17... ONNX: export success ✅ 4.3s, saved as '/content/drive/MyDrive/Collision/final_training2/weights/best.onnx' (166.5 MB) Export complete (8.2s) Results saved to /content/drive/MyDrive/Collision/final_training2/weights Predict: yolo predict task=detect model=/content/drive/MyDrive/Collision/final_training2/weights/best.onnx imgsz=224 Validate: yolo val task=detect model=/content/drive/MyDrive/Collision/final_training2/weights/best.onnx imgsz=224 data=/content/drive/MyDrive/Collision/data.yaml Visualize: https://netron.app
Out[ ]:
'/content/drive/MyDrive/Collision/final_training2/weights/best.onnx'
In [ ]:
import requests
from PIL import Image
import matplotlib.pyplot as plt
from io import BytesIO
# URL of the image you want to display
image_url = "https://images.prismic.io/encord/18732cf0-dd15-4c3d-94b5-401d7266c000_YOLOv8+Layout.webp"
# Download the image from the URL
response = requests.get(image_url)
image = Image.open(BytesIO(response.content))
plt.figure(figsize=(30, 30)) # You can adjust the size as needed
# Display the image in Colab using matplotlib.pyplot
plt.imshow(image)
plt.axis('off')
plt.show()
In [ ]:
image = Image.open("/content/drive/MyDrive/Collision/final_training2/P_curve.png")
plt.figure(figsize=(30, 30)) # You can adjust the size as needed
# Display the image in Colab using matplotlib.pyplot
plt.imshow(image)
plt.axis('off')
plt.show()
In [ ]:
image = Image.open("/content/drive/MyDrive/Collision/final_training2/F1_curve.png")
plt.figure(figsize=(30, 30)) # You can adjust the size as needed
# Display the image in Colab using matplotlib.pyplot
plt.imshow(image)
plt.axis('off')
plt.show()
In [ ]:
image = Image.open("/content/drive/MyDrive/Collision/final_training2/R_curve.png")
plt.figure(figsize=(30, 30)) # You can adjust the size as needed
# Display the image in Colab using matplotlib.pyplot
plt.imshow(image)
plt.axis('off')
plt.show()
In [ ]:
image = Image.open("/content/drive/MyDrive/Collision/final_training2/PR_curve.png")
plt.figure(figsize=(30, 30)) # You can adjust the size as needed
# Display the image in Colab using matplotlib.pyplot
plt.imshow(image)
plt.axis('off')
plt.show()
In [ ]:
# import matplotlib.pyplot as plt
# # Testing accuracy list
# testing_acclist = [0.71903, 0.60838, 0.55655, 0.59706, 0.61338, 0.63144, 0.68842, 0.71749, 0.72123, 0.76903]
# # Training accuracy list
# training_acclist = [0.73759, 0.61301, 0.58692, 0.63492, 0.62585, 0.66607, 0.70197, 0.73595, 0.78802, 0.81798]
# # Setting the plot style
# plt.style.use('dark_background')
# # Plotting the accuracy
# plt.figure(figsize=(8, 6))
# epochs = range(1, len(testing_acclist) + 1)
# plt.plot(epochs, training_acclist, label='Training Accuracy', color='lightblue', linestyle='dashed', linewidth=2)
# plt.plot(epochs, testing_acclist, label='Testing Accuracy', color='salmon', linestyle='dotted', linewidth=2)
# plt.title('Model Accuracy', fontsize=15, fontweight='bold')
# plt.xlabel('Epochs', fontsize=12)
# plt.ylabel('Accuracy', fontsize=12)
# plt.legend()
# plt.grid(color='gray', linestyle='--', linewidth=0.5)
# plt.show()
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
In [ ]:
!yolo predict model="/content/drive/MyDrive/Collision/training/weights/best.pt" source='/content/drive/MyDrive/Collision/test/images/images_491--2-_jpg.rf.6ca6ea005ddad7b542418f918362377d.jpg' imgsz=640
Ultralytics YOLOv8.0.211 🚀 Python-3.10.12 torch-2.1.0+cu118 CPU (Intel Xeon 2.00GHz)
Model summary (fused): 168 layers, 3006623 parameters, 0 gradients, 8.1 GFLOPs
image 1/1 /content/drive/MyDrive/Collision/test/images/images_491--2-_jpg.rf.6ca6ea005ddad7b542418f918362377d.jpg: 640x640 2 minors, 1 moderate, 201.2ms
Speed: 6.9ms preprocess, 201.2ms inference, 1.3ms postprocess per image at shape (1, 3, 640, 640)
Results saved to runs/detect/predict3
💡 Learn more at https://docs.ultralytics.com/modes/predict
In [ ]:
!yolo predict model="/content/drive/MyDrive/Collision/training/weights/best.pt" source='https://www.motorbeam.com/wp-content/uploads/Tata-Punch-Fire-Accident.jpg' imgsz=640
Ultralytics YOLOv8.0.211 🚀 Python-3.10.12 torch-2.1.0+cu118 CPU (Intel Xeon 2.00GHz)
Model summary (fused): 168 layers, 3006623 parameters, 0 gradients, 8.1 GFLOPs
Downloading https://www.motorbeam.com/wp-content/uploads/Tata-Punch-Fire-Accident.jpg to 'Tata-Punch-Fire-Accident.jpg'...
100% 114k/114k [00:00<00:00, 194kB/s]
image 1/1 /content/Tata-Punch-Fire-Accident.jpg: 576x640 1 fire, 1 severe, 316.1ms
Speed: 32.6ms preprocess, 316.1ms inference, 1.6ms postprocess per image at shape (1, 3, 576, 640)
Results saved to runs/detect/predict5
💡 Learn more at https://docs.ultralytics.com/modes/predict
In [ ]: